Clustering of clinical symptoms using large language models reveals low diagnostic specificity of proposed alternatives to consensus mast cell activation syndrome criteria
2024

Low Diagnostic Specificity of Alternative Mast Cell Activation Syndrome Criteria

publication Evidence: moderate

Author Information

Author(s): Solomon Benjamin D. MD, PhD, Khatri Purvesh PhD

Primary Institution: Stanford University

Hypothesis

Do alternative MCAS criteria result in less concise or consistent diagnostic alternatives, reducing diagnostic specificity?

Conclusion

Alternative MCAS criteria are associated with a distinct set of diagnoses compared to consortium MCAS criteria and have lower diagnostic consistency.

Supporting Evidence

  • Alternative MCAS criteria are associated with more variable diagnoses compared to consortium MCAS criteria.
  • The Shannon diversity of alternative MCAS criteria diagnoses was significantly higher than consortium MCAS criteria diagnoses.
  • Alternative MCAS criteria overlap with a highly variable range of possible diagnoses.

Takeaway

The study shows that using different criteria for diagnosing mast cell activation syndrome can lead to confusion and misdiagnosis because they are not as specific.

Methodology

The study used large language models to analyze the diagnostic precision and specificity of consortium and alternative MCAS criteria.

Potential Biases

The use of alternative criteria may lead to overdiagnosis and mismanagement of patients.

Limitations

The training data for large language models includes a wide range of public text sources, which may not be restricted to medical literature.

Statistical Information

P-Value

0.004

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1016/j.jaci.2024.09.006

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication